List of usage examples for org.apache.hadoop.mapreduce Job setJobName
public void setJobName(String name) throws IllegalStateException
From source file:com.linkedin.thirdeye.bootstrap.segment.create.SegmentCreationPhaseJob.java
License:Apache License
public Job run() throws Exception { Job job = Job.getInstance(getConf()); job.setJarByClass(SegmentCreationPhaseJob.class); job.setJobName(name); FileSystem fs = FileSystem.get(getConf()); Configuration configuration = job.getConfiguration(); String schemaPath = getAndSetConfiguration(configuration, SEGMENT_CREATION_SCHEMA_PATH); LOGGER.info("Schema path : {}", schemaPath); String configPath = getAndSetConfiguration(configuration, SEGMENT_CREATION_CONFIG_PATH); LOGGER.info("Config path : {}", configPath); Schema dataSchema = createSchema(configPath); LOGGER.info("Data schema : {}", dataSchema); String inputSegmentDir = getAndSetConfiguration(configuration, SEGMENT_CREATION_INPUT_PATH); LOGGER.info("Input path : {}", inputSegmentDir); String outputDir = getAndSetConfiguration(configuration, SEGMENT_CREATION_OUTPUT_PATH); LOGGER.info("Output path : {}", outputDir); String stagingDir = new File(outputDir, TEMP).getAbsolutePath(); LOGGER.info("Staging dir : {}", stagingDir); String tableName = getAndSetConfiguration(configuration, SEGMENT_CREATION_SEGMENT_TABLE_NAME); LOGGER.info("Segment table name : {}", tableName); // Create temporary directory if (fs.exists(new Path(stagingDir))) { LOGGER.warn("Found the temp folder, deleting it"); fs.delete(new Path(stagingDir), true); }//from ww w.j a v a 2 s. c o m fs.mkdirs(new Path(stagingDir)); fs.mkdirs(new Path(stagingDir + "/input/")); if (fs.exists(new Path(outputDir))) { LOGGER.warn("Found the output folder deleting it"); fs.delete(new Path(outputDir), true); } fs.mkdirs(new Path(outputDir)); Path inputPathPattern = new Path(inputSegmentDir); List<FileStatus> inputDataFiles = Arrays.asList(fs.listStatus(inputPathPattern)); LOGGER.info("size {}", inputDataFiles.size()); try { for (int seqId = 0; seqId < inputDataFiles.size(); ++seqId) { FileStatus file = inputDataFiles.get(seqId); String completeFilePath = " " + file.getPath().toString() + " " + seqId; Path newOutPutFile = new Path((stagingDir + "/input/" + file.getPath().toString().replace('.', '_').replace('/', '_').replace(':', '_') + ".txt")); FSDataOutputStream stream = fs.create(newOutPutFile); LOGGER.info("wrote {}", completeFilePath); stream.writeUTF(completeFilePath); stream.flush(); stream.close(); } } catch (Exception e) { LOGGER.error("Exception while reading input files ", e); } job.setMapperClass(SegmentCreationPhaseMapReduceJob.SegmentCreationMapper.class); if (System.getenv("HADOOP_TOKEN_FILE_LOCATION") != null) { job.getConfiguration().set("mapreduce.job.credentials.binary", System.getenv("HADOOP_TOKEN_FILE_LOCATION")); } job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(stagingDir + "/input/")); FileOutputFormat.setOutputPath(job, new Path(stagingDir + "/output/")); job.getConfiguration().setInt(JobContext.NUM_MAPS, inputDataFiles.size()); job.getConfiguration().set("data.schema", OBJECT_MAPPER.writeValueAsString(dataSchema)); if (!fs.exists(new Path(schemaPath))) { OBJECT_MAPPER.writerWithDefaultPrettyPrinter().writeValue(fs.create(new Path(schemaPath), false), dataSchema); } job.setMaxReduceAttempts(1); job.setMaxMapAttempts(0); job.setNumReduceTasks(0); for (Object key : props.keySet()) { job.getConfiguration().set(key.toString(), props.getProperty(key.toString())); } job.waitForCompletion(true); if (!job.isSuccessful()) { throw new RuntimeException("Job failed : " + job); } LOGGER.info("Moving Segment Tar files from {} to: {}", stagingDir + "/output/segmentTar", outputDir); FileStatus[] segmentArr = fs.listStatus(new Path(stagingDir + "/output/segmentTar")); for (FileStatus segment : segmentArr) { fs.rename(segment.getPath(), new Path(outputDir, segment.getPath().getName())); } // Delete temporary directory. LOGGER.info("Cleanup the working directory."); LOGGER.info("Deleting the dir: {}", stagingDir); fs.delete(new Path(stagingDir), true); return job; }
From source file:com.linkedin.thirdeye.hadoop.aggregation.AggregationPhaseJob.java
License:Apache License
public Job run() throws Exception { Job job = Job.getInstance(getConf()); job.setJobName(name); job.setJarByClass(AggregationPhaseJob.class); FileSystem fs = FileSystem.get(getConf()); Configuration configuration = job.getConfiguration(); // Properties LOGGER.info("Properties {}", props); // Input Path String inputPathDir = getAndSetConfiguration(configuration, AGG_PHASE_INPUT_PATH); LOGGER.info("Input path dir: " + inputPathDir); for (String inputPath : inputPathDir.split(ThirdEyeConstants.FIELD_SEPARATOR)) { LOGGER.info("Adding input:" + inputPath); Path input = new Path(inputPath); FileInputFormat.addInputPath(job, input); }/*from w ww . j av a 2s .c o m*/ // Output path Path outputPath = new Path(getAndSetConfiguration(configuration, AGG_PHASE_OUTPUT_PATH)); LOGGER.info("Output path dir: " + outputPath.toString()); if (fs.exists(outputPath)) { fs.delete(outputPath, true); } FileOutputFormat.setOutputPath(job, outputPath); // Schema Schema avroSchema = ThirdeyeAvroUtils.getSchema(inputPathDir); LOGGER.info("Schema : {}", avroSchema.toString(true)); job.getConfiguration().set(AGG_PHASE_AVRO_SCHEMA.toString(), avroSchema.toString()); // ThirdEyeConfig String metricTypesProperty = ThirdeyeAvroUtils.getMetricTypesProperty( props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_NAMES.toString()), props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString()), avroSchema); props.setProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString(), metricTypesProperty); ThirdEyeConfig thirdeyeConfig = ThirdEyeConfig.fromProperties(props); LOGGER.info("Thirdeye Config {}", thirdeyeConfig.encode()); job.getConfiguration().set(AGG_PHASE_THIRDEYE_CONFIG.toString(), OBJECT_MAPPER.writeValueAsString(thirdeyeConfig)); // Map config job.setMapperClass(AggregationMapper.class); job.setInputFormatClass(AvroKeyInputFormat.class); job.setMapOutputKeyClass(BytesWritable.class); job.setMapOutputValueClass(BytesWritable.class); // Reduce config job.setReducerClass(AggregationReducer.class); job.setOutputKeyClass(AvroKey.class); job.setOutputValueClass(NullWritable.class); AvroJob.setOutputKeySchema(job, avroSchema); job.setOutputFormatClass(AvroKeyOutputFormat.class); String numReducers = props.getProperty(ThirdEyeJobProperties.THIRDEYE_NUM_REDUCERS.getName()); LOGGER.info("Num Reducers : {}", numReducers); if (StringUtils.isNotBlank(numReducers)) { job.setNumReduceTasks(Integer.valueOf(numReducers)); LOGGER.info("Setting num reducers {}", job.getNumReduceTasks()); } job.waitForCompletion(true); Counter counter = job.getCounters().findCounter(AggregationCounter.NUMBER_OF_RECORDS); LOGGER.info(counter.getDisplayName() + " : " + counter.getValue()); if (counter.getValue() == 0) { throw new IllegalStateException("No input records in " + inputPathDir); } counter = job.getCounters().findCounter(AggregationCounter.NUMBER_OF_RECORDS_FLATTENED); LOGGER.info(counter.getDisplayName() + " : " + counter.getValue()); for (String metric : thirdeyeConfig.getMetricNames()) { counter = job.getCounters().findCounter(thirdeyeConfig.getCollection(), metric); LOGGER.info(counter.getDisplayName() + " : " + counter.getValue()); } return job; }
From source file:com.linkedin.thirdeye.hadoop.backfill.BackfillPhaseJob.java
License:Apache License
public Job run() throws Exception { Job job = Job.getInstance(getConf()); job.setJarByClass(BackfillPhaseJob.class); job.setJobName(name); FileSystem fs = FileSystem.get(getConf()); Configuration configuration = job.getConfiguration(); LOGGER.info("*******************************************************************************"); String controllerHost = getAndSetConfiguration(configuration, BACKFILL_PHASE_CONTROLLER_HOST); String controllerPort = getAndSetConfiguration(configuration, BACKFILL_PHASE_CONTROLLER_PORT); LOGGER.info("Controller Host : {} Controller Port : {}", controllerHost, controllerPort); String segmentStartTime = getAndSetConfiguration(configuration, BACKFILL_PHASE_START_TIME); String segmentEndTime = getAndSetConfiguration(configuration, BACKFILL_PHASE_END_TIME); long startTime = Long.valueOf(segmentStartTime); long endTime = Long.valueOf(segmentEndTime); if (Long.valueOf(segmentStartTime) > Long.valueOf(segmentEndTime)) { throw new IllegalStateException("Start time cannot be greater than end time"); }//w w w . ja v a 2 s.c o m String tableName = getAndSetConfiguration(configuration, BACKFILL_PHASE_TABLE_NAME); LOGGER.info("Start time : {} End time : {} Table name : {}", segmentStartTime, segmentEndTime, tableName); String outputPath = getAndSetConfiguration(configuration, BACKFILL_PHASE_OUTPUT_PATH); LOGGER.info("Output path : {}", outputPath); Path backfillDir = new Path(outputPath); if (fs.exists(backfillDir)) { LOGGER.warn("Found the output folder deleting it"); fs.delete(backfillDir, true); } Path downloadDir = new Path(backfillDir, DOWNLOAD); LOGGER.info("Creating download dir : {}", downloadDir); fs.mkdirs(downloadDir); Path inputDir = new Path(backfillDir, INPUT); LOGGER.info("Creating input dir : {}", inputDir); fs.mkdirs(inputDir); Path outputDir = new Path(backfillDir, OUTPUT); LOGGER.info("Creating output dir : {}", outputDir); BackfillControllerAPIs backfillControllerAPIs = new BackfillControllerAPIs(controllerHost, Integer.valueOf(controllerPort), tableName); LOGGER.info("Downloading segments in range {} to {}", startTime, endTime); List<String> allSegments = backfillControllerAPIs.getAllSegments(tableName); List<String> segmentsToDownload = backfillControllerAPIs.findSegmentsInRange(tableName, allSegments, startTime, endTime); for (String segmentName : segmentsToDownload) { backfillControllerAPIs.downloadSegment(segmentName, downloadDir); } LOGGER.info("Reading downloaded segment input files"); List<FileStatus> inputDataFiles = new ArrayList<>(); inputDataFiles.addAll(Lists.newArrayList(fs.listStatus(downloadDir))); LOGGER.info("size {}", inputDataFiles.size()); try { LOGGER.info("Creating input files at {} for segment input files", inputDir); for (int seqId = 0; seqId < inputDataFiles.size(); ++seqId) { FileStatus file = inputDataFiles.get(seqId); String completeFilePath = " " + file.getPath().toString() + " " + seqId; Path newOutPutFile = new Path((inputDir + "/" + file.getPath().toString().replace('.', '_').replace('/', '_').replace(':', '_') + ".txt")); FSDataOutputStream stream = fs.create(newOutPutFile); LOGGER.info("wrote {}", completeFilePath); stream.writeUTF(completeFilePath); stream.flush(); stream.close(); } } catch (Exception e) { LOGGER.error("Exception while reading input files ", e); } job.setMapperClass(BackfillPhaseMapJob.BackfillMapper.class); if (System.getenv("HADOOP_TOKEN_FILE_LOCATION") != null) { job.getConfiguration().set("mapreduce.job.credentials.binary", System.getenv("HADOOP_TOKEN_FILE_LOCATION")); } job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); FileInputFormat.addInputPath(job, inputDir); FileOutputFormat.setOutputPath(job, outputDir); job.getConfiguration().setInt(JobContext.NUM_MAPS, inputDataFiles.size()); job.setMaxReduceAttempts(1); job.setMaxMapAttempts(0); job.setNumReduceTasks(0); for (Object key : props.keySet()) { job.getConfiguration().set(key.toString(), props.getProperty(key.toString())); } job.waitForCompletion(true); if (!job.isSuccessful()) { throw new RuntimeException("Job failed : " + job); } LOGGER.info("Cleanup the working directory"); LOGGER.info("Deleting the dir: {}", downloadDir); fs.delete(downloadDir, true); LOGGER.info("Deleting the dir: {}", inputDir); fs.delete(inputDir, true); LOGGER.info("Deleting the dir: {}", outputDir); fs.delete(outputDir, true); return job; }
From source file:com.linkedin.thirdeye.hadoop.derivedcolumn.transformation.DerivedColumnTransformationPhaseJob.java
License:Apache License
public Job run() throws Exception { Job job = Job.getInstance(getConf()); job.setJobName(name); job.setJarByClass(DerivedColumnTransformationPhaseJob.class); Configuration configuration = job.getConfiguration(); FileSystem fs = FileSystem.get(configuration); // Input Path String inputPathDir = getAndSetConfiguration(configuration, DERIVED_COLUMN_TRANSFORMATION_PHASE_INPUT_PATH); LOGGER.info("Input path dir: " + inputPathDir); for (String inputPath : inputPathDir.split(",")) { LOGGER.info("Adding input:" + inputPath); Path input = new Path(inputPath); FileInputFormat.addInputPath(job, input); }/* w w w . ja va 2s.c o m*/ // Topk path String topkPath = getAndSetConfiguration(configuration, DERIVED_COLUMN_TRANSFORMATION_PHASE_TOPK_PATH); LOGGER.info("Topk path : " + topkPath); // Output path Path outputPath = new Path( getAndSetConfiguration(configuration, DERIVED_COLUMN_TRANSFORMATION_PHASE_OUTPUT_PATH)); LOGGER.info("Output path dir: " + outputPath.toString()); if (fs.exists(outputPath)) { fs.delete(outputPath, true); } FileOutputFormat.setOutputPath(job, outputPath); // Schema Schema avroSchema = ThirdeyeAvroUtils.getSchema(inputPathDir); LOGGER.info("Schema : {}", avroSchema.toString(true)); // ThirdEyeConfig String metricTypesProperty = ThirdeyeAvroUtils.getMetricTypesProperty( props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_NAMES.toString()), props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString()), avroSchema); props.setProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString(), metricTypesProperty); ThirdEyeConfig thirdeyeConfig = ThirdEyeConfig.fromProperties(props); job.getConfiguration().set(DERIVED_COLUMN_TRANSFORMATION_PHASE_THIRDEYE_CONFIG.toString(), OBJECT_MAPPER.writeValueAsString(thirdeyeConfig)); LOGGER.info("ThirdEyeConfig {}", thirdeyeConfig.encode()); // New schema Schema outputSchema = newSchema(thirdeyeConfig); job.getConfiguration().set(DERIVED_COLUMN_TRANSFORMATION_PHASE_OUTPUT_SCHEMA.toString(), outputSchema.toString()); // Map config job.setMapperClass(DerivedColumnTransformationPhaseMapper.class); job.setInputFormatClass(AvroKeyInputFormat.class); job.setMapOutputKeyClass(AvroKey.class); job.setMapOutputValueClass(NullWritable.class); AvroJob.setOutputKeySchema(job, outputSchema); LazyOutputFormat.setOutputFormatClass(job, AvroKeyOutputFormat.class); AvroMultipleOutputs.addNamedOutput(job, "avro", AvroKeyOutputFormat.class, outputSchema); job.setNumReduceTasks(0); job.waitForCompletion(true); return job; }
From source file:com.linkedin.thirdeye.hadoop.segment.creation.SegmentCreationPhaseJob.java
License:Apache License
public Job run() throws Exception { Job job = Job.getInstance(getConf()); job.setJarByClass(SegmentCreationPhaseJob.class); job.setJobName(name); FileSystem fs = FileSystem.get(getConf()); Configuration configuration = job.getConfiguration(); String inputSegmentDir = getAndSetConfiguration(configuration, SEGMENT_CREATION_INPUT_PATH); LOGGER.info("Input path : {}", inputSegmentDir); Schema avroSchema = ThirdeyeAvroUtils.getSchema(inputSegmentDir); LOGGER.info("Schema : {}", avroSchema); String metricTypesProperty = ThirdeyeAvroUtils.getMetricTypesProperty( props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_NAMES.toString()), props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString()), avroSchema); props.setProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString(), metricTypesProperty); ThirdEyeConfig thirdeyeConfig = ThirdEyeConfig.fromProperties(props); LOGGER.info("ThirdEyeConfig {}", thirdeyeConfig.encode()); String outputDir = getAndSetConfiguration(configuration, SEGMENT_CREATION_OUTPUT_PATH); LOGGER.info("Output path : {}", outputDir); Path stagingDir = new Path(outputDir, TEMP); LOGGER.info("Staging dir : {}", stagingDir); String segmentWallClockStart = getAndSetConfiguration(configuration, SEGMENT_CREATION_WALLCLOCK_START_TIME); LOGGER.info("Segment wallclock start time : {}", segmentWallClockStart); String segmentWallClockEnd = getAndSetConfiguration(configuration, SEGMENT_CREATION_WALLCLOCK_END_TIME); LOGGER.info("Segment wallclock end time : {}", segmentWallClockEnd); String schedule = getAndSetConfiguration(configuration, SEGMENT_CREATION_SCHEDULE); LOGGER.info("Segment schedule : {}", schedule); String isBackfill = props.getProperty(SEGMENT_CREATION_BACKFILL.toString(), DEFAULT_BACKFILL); configuration.set(SEGMENT_CREATION_BACKFILL.toString(), isBackfill); LOGGER.info("Is Backfill : {}", configuration.get(SEGMENT_CREATION_BACKFILL.toString())); // Create temporary directory if (fs.exists(stagingDir)) { LOGGER.warn("Found the temp folder, deleting it"); fs.delete(stagingDir, true);/*from w w w . j av a 2 s . c om*/ } fs.mkdirs(stagingDir); fs.mkdirs(new Path(stagingDir + "/input/")); // Create output directory if (fs.exists(new Path(outputDir))) { LOGGER.warn("Found the output folder deleting it"); fs.delete(new Path(outputDir), true); } fs.mkdirs(new Path(outputDir)); // Read input files List<FileStatus> inputDataFiles = new ArrayList<>(); for (String input : inputSegmentDir.split(",")) { Path inputPathPattern = new Path(input); inputDataFiles.addAll(Arrays.asList(fs.listStatus(inputPathPattern))); } LOGGER.info("size {}", inputDataFiles.size()); try { for (int seqId = 0; seqId < inputDataFiles.size(); ++seqId) { FileStatus file = inputDataFiles.get(seqId); String completeFilePath = " " + file.getPath().toString() + " " + seqId; Path newOutPutFile = new Path((stagingDir + "/input/" + file.getPath().toString().replace('.', '_').replace('/', '_').replace(':', '_') + ".txt")); FSDataOutputStream stream = fs.create(newOutPutFile); LOGGER.info("wrote {}", completeFilePath); stream.writeUTF(completeFilePath); stream.flush(); stream.close(); } } catch (Exception e) { LOGGER.error("Exception while reading input files ", e); } job.setMapperClass(SegmentCreationPhaseMapReduceJob.SegmentCreationMapper.class); if (System.getenv("HADOOP_TOKEN_FILE_LOCATION") != null) { job.getConfiguration().set("mapreduce.job.credentials.binary", System.getenv("HADOOP_TOKEN_FILE_LOCATION")); } job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(stagingDir + "/input/")); FileOutputFormat.setOutputPath(job, new Path(stagingDir + "/output/")); job.getConfiguration().setInt(JobContext.NUM_MAPS, inputDataFiles.size()); job.getConfiguration().set(SEGMENT_CREATION_THIRDEYE_CONFIG.toString(), OBJECT_MAPPER.writeValueAsString(thirdeyeConfig)); job.setMaxReduceAttempts(1); job.setMaxMapAttempts(0); job.setNumReduceTasks(0); for (Object key : props.keySet()) { job.getConfiguration().set(key.toString(), props.getProperty(key.toString())); } job.waitForCompletion(true); if (!job.isSuccessful()) { throw new RuntimeException("Job failed : " + job); } LOGGER.info("Moving Segment Tar files from {} to: {}", stagingDir + "/output/segmentTar", outputDir); FileStatus[] segmentArr = fs.listStatus(new Path(stagingDir + "/output/segmentTar")); for (FileStatus segment : segmentArr) { fs.rename(segment.getPath(), new Path(outputDir, segment.getPath().getName())); } // Delete temporary directory. LOGGER.info("Cleanup the working directory."); LOGGER.info("Deleting the dir: {}", stagingDir); fs.delete(stagingDir, true); return job; }
From source file:com.linkedin.thirdeye.hadoop.topk.TopKPhaseJob.java
License:Apache License
public Job run() throws Exception { Job job = Job.getInstance(getConf()); job.setJobName(name); job.setJarByClass(TopKPhaseJob.class); Configuration configuration = job.getConfiguration(); FileSystem fs = FileSystem.get(configuration); // Properties LOGGER.info("Properties {}", props); // Input Path String inputPathDir = getAndSetConfiguration(configuration, TOPK_PHASE_INPUT_PATH); LOGGER.info("Input path dir: " + inputPathDir); for (String inputPath : inputPathDir.split(ThirdEyeConstants.FIELD_SEPARATOR)) { LOGGER.info("Adding input:" + inputPath); Path input = new Path(inputPath); FileInputFormat.addInputPath(job, input); }//from w ww . jav a2 s. c o m // Output path Path outputPath = new Path(getAndSetConfiguration(configuration, TOPK_PHASE_OUTPUT_PATH)); LOGGER.info("Output path dir: " + outputPath.toString()); if (fs.exists(outputPath)) { fs.delete(outputPath, true); } FileOutputFormat.setOutputPath(job, outputPath); // Schema Schema avroSchema = ThirdeyeAvroUtils.getSchema(inputPathDir); LOGGER.info("Schema : {}", avroSchema.toString(true)); // ThirdEyeConfig String metricTypesProperty = ThirdeyeAvroUtils.getMetricTypesProperty( props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_NAMES.toString()), props.getProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString()), avroSchema); props.setProperty(ThirdEyeConfigProperties.THIRDEYE_METRIC_TYPES.toString(), metricTypesProperty); ThirdEyeConfig thirdeyeConfig = ThirdEyeConfig.fromProperties(props); LOGGER.info("Thirdeye Config {}", thirdeyeConfig.encode()); job.getConfiguration().set(TOPK_PHASE_THIRDEYE_CONFIG.toString(), OBJECT_MAPPER.writeValueAsString(thirdeyeConfig)); // Map config job.setMapperClass(TopKPhaseMapper.class); job.setInputFormatClass(AvroKeyInputFormat.class); job.setMapOutputKeyClass(BytesWritable.class); job.setMapOutputValueClass(BytesWritable.class); // Combiner job.setCombinerClass(TopKPhaseCombiner.class); // Reduce config job.setReducerClass(TopKPhaseReducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(NullWritable.class); job.setNumReduceTasks(1); job.waitForCompletion(true); return job; }
From source file:com.marklogic.hadoop.csvtoxml.CsvToXML.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); @SuppressWarnings("deprecation") Job job = new Job(conf); job.setJobName("ProcessCSVtoXML_job"); System.out.println("After the JobName Updates"); job.setJarByClass(CsvToXML.class); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(ContentMapper.class); job.setMapOutputKeyClass(DocumentURI.class); job.setMapOutputValueClass(Text.class); job.setOutputFormatClass(ContentOutputFormat.class); System.out.println("Made it past external jar dependencies nodes"); FileInputFormat.setInputPaths(job, new Path(otherArgs[1])); conf = job.getConfiguration();/*from ww w.ja va 2s.c o m*/ conf.addResource(otherArgs[0]); System.out.println("After the conf.set"); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.ml.hadoop.nlp.DocumentProcessor.java
License:Apache License
/** * Convert the input documents into token array using the {@link StringTuple} The input documents has to be * in the {@link org.apache.hadoop.io.SequenceFile} format * //from w ww .j a v a 2 s.c o m * @param input * input directory of the documents in {@link org.apache.hadoop.io.SequenceFile} format * @param output * output directory were the {@link StringTuple} token array of each document has to be created * @param analyzerClass * The Lucene {@link Analyzer} for tokenizing the UTF-8 text */ public static void tokenizeDocuments(Path input, Class<? extends Analyzer> analyzerClass, Path output, Configuration baseConf) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(baseConf); // this conf parameter needs to be set enable serialisation of conf values conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization," + "org.apache.hadoop.io.serializer.WritableSerialization"); conf.set(ANALYZER_CLASS, analyzerClass.getName()); Job job = new Job(conf); job.setJobName("DocumentProcessor::DocumentTokenizer: input-folder: " + input); job.setJarByClass(DocumentProcessor.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(StringTuple.class); FileInputFormat.setInputPaths(job, input); FileOutputFormat.setOutputPath(job, output); job.setMapperClass(SequenceFileTokenizerMapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setNumReduceTasks(0); job.setOutputFormatClass(SequenceFileOutputFormat.class); HadoopUtil.delete(conf, output); boolean succeeded = job.waitForCompletion(true); if (!succeeded) { throw new IllegalStateException("Job failed!"); } }
From source file:com.moz.fiji.mapreduce.bulkimport.FijiBulkImportJobBuilder.java
License:Apache License
/** {@inheritDoc} */ @Override/* w w w . jav a 2 s .co m*/ protected void configureJob(Job job) throws IOException { final Configuration conf = job.getConfiguration(); // Store the name of the the importer to use in the job configuration so the mapper can // create instances of it. // Construct the bulk importer instance. if (null == mBulkImporterClass) { throw new JobConfigurationException("Must specify a bulk importer."); } conf.setClass(FijiConfKeys.FIJI_BULK_IMPORTER_CLASS, mBulkImporterClass, FijiBulkImporter.class); mJobOutput.configure(job); // Configure the mapper and reducer. This part depends on whether we're going to write // to HFiles or directly to the table. configureJobForHFileOutput(job); job.setJobName("Fiji bulk import: " + mBulkImporterClass.getSimpleName()); mBulkImporter = ReflectionUtils.newInstance(mBulkImporterClass, conf); // Configure the MapReduce job (requires mBulkImporter to be set properly): super.configureJob(job); }
From source file:com.moz.fiji.mapreduce.FijiMapReduceJobBuilder.java
License:Apache License
/** {@inheritDoc} */ @Override//from w w w .j a v a 2 s .c om protected void configureJob(Job job) throws IOException { // Check that job input was configured. if (null == mJobInput) { throw new JobConfigurationException("Must specify job input."); } // Construct the mapper instance. if (null == mMapperClass) { throw new JobConfigurationException("Must specify a mapper."); } mMapper = ReflectionUtils.newInstance(mMapperClass, job.getConfiguration()); // Construct the combiner instance (if specified). if (null != mCombinerClass) { mCombiner = ReflectionUtils.newInstance(mCombinerClass, job.getConfiguration()); } // Construct the reducer instance (if specified). if (null != mReducerClass) { mReducer = ReflectionUtils.newInstance(mReducerClass, job.getConfiguration()); } StringBuilder name = new StringBuilder(); name.append("Fiji transform: "); name.append(mMapperClass.getSimpleName()); if (null != mReducerClass) { name.append(" / "); name.append(mReducerClass.getSimpleName()); } job.setJobName(name.toString()); // Configure the MapReduce job. super.configureJob(job); }